Loading
DARIUS
Digital Argumentation Instruction for Science
The Deutsche Telekom Foundation is funding "DARIUS -Digital Argumentation Instruction for Science". The project working group is investigating how students' written scientific argumentation can be promoted with the help of automated formative assessments.
Project data
| Research lines | Research Line Domain-Specific Learning in Preschools and Schools, Research Line Methodological Research and Machine Learning | ||
| Departments | Chemistry Education, Educational Research and Educational Psychology | ||
| Funding | Deutsche Telekom Stiftung (7/1/2021–6/30/2024) | ||
| Period | 7/1/2021–7/31/2024 | ||
| Status | completed | ||
| IPN researchers | Dr. Thorben Jansen (Project lead), Jan Luca Bahr, Dr. Lars Ingver Höft, M. A. Nils-Jonathan Schaller | ||
The Junior Research Group DARIUS investigates how automated formative assessment can promote students' written argumentations.
The project aims to develop and evaluate a digital learning tool for students and teachers. Students will receive automated feedback on their writing, showing which additional perspectives would improve their argumentation and which arguments would benefit from further data or explanations. Teachers will get an overview of the strengths and weaknesses in their students' written argumentations. Machine learning algorithms automatically analyze students writing and provide students and teachers with the information. Using the tool, students should improve their argumentative competencies, and teachers receive important guidance to adapt their instructions to their students' needs.
We develop argumentation tasks on controversial, socially relevant, real-world problems informed by science (socio-scientific issues), which are situated in the context of climate change. As the basis of our machine learning model, we ask 1000 secondary school students to complete the tasks. Two specially trained raters will rate each argument's content and structure in every text in the resulting corpus. In the following, we use the texts and ratings to train a machine-learning algorithm to automate the assessment and integrate the algorithm into our learning tool. Finally, evaluating and optimizing our learning tool, we will conduct experimental studies to investigate moderators (e.g., amount of feedback, feedback timing) of the effectiveness of adaptive feedback on performance. The project is funded by Deutsche Telekom-Stiftung. The project duration is three years (2021-2024).
Leader: Dr. Thorben Jansen (Psychology)
Group members: Dr. Lars Höft (Chemistry Education), Nils Jonathan Schaller (Computational Linguistics), Luca Bahr (Psychology)
Contact: tjansen@leibniz-ipn.de
